[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-269378-105":59,"doc-detail-269378-en":131},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":124,"head_meta":126,"extra_data":128,"updated_unix":130},105,"en","sparks-of-artificial-general-recommender-agr-early-experiments-with-chatgpt","Sparks of Artificial General Recommender (AGR) - Early Experiments with ChatGPT","","This study investigates the feasibility of developing an Artificial General Recommender (AGR) enabled by recent Large Language Model (LLM) advances. An AGR combines conversationality and universality to conduct natural dialogues and produce recommendations across multiple domains. The paper proposes ten AGR principles, each paired with testing protocols, and evaluates whether ChatGPT can satisfy them through recommendation-oriented dialogues. Results indicate promising potential alongside limitations and improvement directions.",{"@graph":69,"@context":123},[70,84,106],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/sparks-of-artificial-general-recommender-agr-early-experiments-with-chatgpt/269378/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/sparks-of-artificial-general-recommender-agr-early-experiments-with-chatgpt/269378.png","ImageObject",300,407,{"name":92,"@type":93},"Connor ","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-29","2026-09-15",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",12,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"What is an Artificial General Recommender (AGR) in this study?","Question",{"text":113,"@type":114},"An AGR is defined as a system combining conversationality and universality. It supports natural dialogues and can perform many tasks to generate personalized recommendations across different item domains.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"How does the paper evaluate whether ChatGPT can function as an AGR?",{"text":118,"@type":114},"For each of the ten AGR principles, the study uses a dedicated testing protocol and conducts recommendation-oriented dialogues with ChatGPT. It observes the model’s behavior and whether it follows the required criteria.",{"name":120,"@type":111,"acceptedAnswer":121},"What do the findings suggest about using ChatGPT as an AGR?",{"text":122,"@type":114},"The results show potential for ChatGPT to serve as an AGR. At the same time, the study identifies several limitations and areas that need improvement.","https://schema.org",{"og:url":83,"og:type":125,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":127,"canonical":83},"index,follow",{"doc_id":129,"site_id":62},269378,1789451027,{"code":4,"msg":5,"data":132},{"doc_id":129,"user_id":133,"nickname":92,"user_avatar":134,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":105,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":52,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":130,"read_time":144,"preview_page_count":4},687207022233,"https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d","Sparks of Artificial General Recommender (AGR): Early Experiments with ChatGPT  \narXiv :2305 .045 18v 1 [ cs .IR] 8 May 2023  \nGuo Lin  \nRutgers University  \nABSTRACT  \nThis study investigates the feasibility of developing an Artificial General Recommender (AGR), facilitated by recent advancementsin Large Language Models(LLMs). AnAGR comprises both conversationality and universality to engage in natural dialogues and generate recommendations across various domains. We propose ten fundamental principles that an AGR should adhere to, each with its corresponding testing protocols. We proceed to assess whether ChatGPT, a sophisticated LLM, can comply with the proposed principles by engaging in recommendation-oriented dialogues with the model while observing its behavior. Our findings demonstrate the potential for ChatGPT to serve as an AGR, though several limitations and areas for improvement are identified.  \nKEYWORDS  \nChatGPT, Artificial General Recommender, Conversational Recommender System, Multi-task Recommender System, Multi-domain Recommender System  \n1 INTRODUCTION  \nRecent advancements in large language models (LLMs) [9, 13, 17, 18, 20] have enabled the possible development of an Artificial General Recommender, denoted as AGR. At its core, an AGR encompasses two primary aspects: (1) Conversationality, implying the ability to engage in interactive, natural dialogues with users, and (2) Universality, signifying the ability to execute a multitude of tasks and generate personalized recommendations for a variety of item domains. In this study, we aim to establish the fundamental principles to which an AGR should adhere. Subsequently, we assess the capacity of ChatGPT, a sophisticated LLM, to serve as an AGR by employing the testing protocols designed for each principle. Drawing from the insights of Microsoft’s reflective paper on GPT testings [4], this study aims to extend and adapt the early experiments on ChatGPT to the domain of Recommender Systems, following a similar instance-based testing approach employed by the referenced paper.  \n2 AGR PRINCIPLES  \nIn this section, we outline ten fundamental principles that an AGR should be capable of achieving. Each principle is accompanied by its definition and corresponding testing protocol. To appraise ChatGPT’s adherence to such principles, we imitate end-users and engage in dialogues with the model to observe its behaviors. We also request the model to perform additional tasks to further examine its alignment with particular principle criteria, as needed.  \nMixed Initiative: to facilitate a natural conversation, both the user and the system should be able to actively participate in the dialogue, rather than limiting the user to initiating interactions while  \nYongfeng Zhang  \nRutgers University  \nthe system merely responds, or using a system that strictly adheres to a pre-determined script for the dialogue [11, 15] . Additionally, users may engage in rapid reading and accidentally overlook or misinterpret some of the system’s utterances [10] . Therefore, the system should exhibit the ability to autonomously initiate actions, including: actively asking questions to solicit user information for more precise recommendations, posing follow-up questions (such as seeking user clarifications) and providing supplementary statements for its previous utterances when necessary [3] .  \n􀀏 Testing Protocol: to assess the model’s ability to proactively initiate actions, we conduct two tests. Firstly, we intentionally provide responses that do not align or are irrelevant with inquiries previously asked by the model, and observe whether the model could determine that the answers provided were not proper for the questions asked and ask for user clarifications. Secondly, we intentionally alter the meaning of words and/or sentences stated in previous model utterances to simulate cases of misreading and compose user input statements with such false assumptions by explicitly referring to them in the statemen","cbCaij3Rk8LOKvnF","https://ap.wps.com/l/cbCaij3Rk8LOKvnF","pdf",193921,"English","# Introduction\n# AGR Principles","[{\"question\":\"What is an Artificial General Recommender (AGR) in this study?\",\"answer\":\"An AGR is defined as a system combining conversationality and universality. It supports natural dialogues and can perform many tasks to generate personalized recommendations across different item domains.\"},{\"question\":\"How does the paper evaluate whether ChatGPT can function as an AGR?\",\"answer\":\"For each of the ten AGR principles, the study uses a dedicated testing protocol and conducts recommendation-oriented dialogues with ChatGPT. It observes the model’s behavior and whether it follows the required criteria.\"},{\"question\":\"What do the findings suggest about using ChatGPT as an AGR?\",\"answer\":\"The results show potential for ChatGPT to serve as an AGR. At the same time, the study identifies several limitations and areas that need improvement.\"}]","Sparks of Artificial General Recommender (AGR) - Early Experiments with ChatGPT | PDF",25]